- Mar 29, 2024
-
-
Grégoire Kubler authored
-
- Mar 28, 2024
-
-
Maxence Naud authored
-
- Mar 26, 2024
-
-
Maxence Naud authored
-
Maxence Naud authored
-
Maxence Naud authored
-
-
Change axes attribute type to allow runtime deduction of 'axes' dimensions in the ReduceMean used in MSE loss function
-
-
-
- Mar 25, 2024
-
-
Maxence Naud authored
-
- Mar 24, 2024
-
-
Maxence Naud authored
Change axes attribute type to allow runtime deduction of 'axes' dimensions in the ReduceMean used in MSE loss function
-
- Mar 22, 2024
-
-
Maxence Naud authored
-
Maxence Naud authored
-
- Mar 18, 2024
-
-
Grégoire Kubler authored
-
- Mar 14, 2024
-
-
Cyril Moineau authored
-
- Mar 05, 2024
-
-
Olivier BICHLER authored
-
Grégoire Kubler authored
-
Grégoire Kubler authored
-
- Mar 04, 2024
-
-
Grégoire Kubler authored
-
- Feb 23, 2024
-
-
Maxence Naud authored
-
- Feb 19, 2024
-
-
Olivier BICHLER authored
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- Feb 18, 2024
-
-
Olivier BICHLER authored
-
- Feb 16, 2024
-
-
Maxence Naud authored
- [function] computation of input dimensions now happens in 'MatMulImpl_cpu::forward()'. It handle indexes and sends the right pointers to its computation kernel - [function] 'getCPUPtr()' new parameter: offset - [function] reduce MatMul kernel function to simple matrices multiplication
-
-
-